IP Library › Granted Patent US 10,790,053
Granted Patent B2
US 10,790,053 · App. 15/489,917 · Granted Sep 29, 2020

Appetite improvement system through memory association

Inventors: Nadiya Kochura (Bolton, MA); Fang Lu (Billerica, MA)
Assignee: International Business Machines Corporation
G16H20/60G06F19/3475G06N20/00G06Q50/01G16H30/40G16H40/63G16H40/67G16H50/20G16H50/70
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,790,053
App. No.
15/489,917
Granted
Sep 29, 2020
Kind
B2
Abstract

Improving appetite through positive memory association. Information is received including text content related to a user. A positive user sentiment is defined using sentiment analysis. Text analysis is applied on the text content to identify a factor in the information that correlates with the positive user sentiment. The factor is ranked based on a strength of the correlation. Responsive to determining that the strength of the correlation is above a predefined threshold, the factor is stored as a positive token. A list of food recipes is accessed to identify a food recipe that incorporates the positive token. The food recipe is displayed to the user.

Claims (54)

1. A computer program product comprising:

one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising:

program instructions to analyze a plurality of user information sources related to a user;

program instructions to define a positive user sentiment expressed by the user in the plurality of user information sources;

program instructions to identify at least one factor that correlates with the positive user sentiment expressed by the user;

program instructions to rank the at least one factor based on a strength of the correlation;

program instructions to, responsive to determining that the strength of the correlation is above a predefined threshold, store the at least one factor as at least one positive token;

program instructions to generate a plurality of food profiles, wherein a respective food item in the plurality of food profiles includes a corresponding recipe information, a corresponding nutritional information, and a corresponding food property information;

program instructions to, responsive to mapping the at least one positive token to the plurality of food profiles, identify, based on the corresponding recipe information, the corresponding nutritional information, and the corresponding food property information, at least one food item that incorporates the at least one positive token, wherein the at least one positive token is associated with the positive sentiment expressed by the user; and

program instructions to continuously update a recommendation list including the at least one food item having a preparation information to resemble the at least one positive token to the user.

2. The computer program product of claim 1 , further comprising:

program instructions to receive at least one image related to the user;

program instructions to define the positive user sentiment with respect to the at least one image based on machine learning techniques; and

program instructions to apply image analysis on the at least one image to identify the at least one factor that correlates with the positive user sentiment.

3. The computer program product of claim 1 , further comprising:

program instructions to receive a brain state data related to the user;

program instructions to define the positive user sentiment with respect to the brain state data based on machine learning techniques; and

program instructions to apply an analysis on the brain state data to identify the at least one factor that correlates with the positive user sentiment.

4. The computer program product of claim 1 , wherein the at least one factor that correlates with the positive user sentiment is selected from the group consisting of:

a theme, a subject, an object, a person, an activity, a setting, an environmental condition, and a time of day.

5. The computer program product of claim 3 , wherein the program instructions to receive the brain state data comprises:

program instructions to monitor the brain state data while the user eats a particular food item; and

program instructions to store the brain state data as being associated with the particular food item.

6. The computer program product of claim 1 , wherein the program instructions to analyze the plurality of user information sources related to the user is selected from the group consisting of:

program instructions to perform image analysis, program instructions to perform text analysis, program instructions to perform natural language processing, program instructions to perform semantic analysis, program instructions to perform sentiment analysis, program instructions to perform rule-based analysis, and program instructions to perform machine learning-based analysis.

7. The computer program product of claim 1 , wherein the program instructions stored on the one or more computer readable storage media further comprises:

program instructions to, responsive to determining that no food item recipe is identified to incorporate the at least one positive token, modify the at least one food item recipe to incorporate the at least one positive token.

8. A computer system comprising:

one or more computer processors;

one or more computer readable storage media;

program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising:

program instructions to analyze a plurality of user information sources related to a user;

program instructions to define a positive user sentiment expressed by the user in the plurality of user information sources;

program instructions to identify at least one factor that correlates with the positive user sentiment expressed by the user;

program instructions to rank the at least one factor based on a strength of the correlation;

program instructions to, responsive to determining that the strength of the correlation is above a predefined threshold, store the at least one factor as at least one positive token;

program instructions to generate a plurality of food profiles, wherein a respective food item in the plurality of food profiles includes a corresponding recipe information, a corresponding nutritional information, and a corresponding food property information;

program instructions to, responsive to mapping the at least one positive token to the plurality of food profiles, identify, based on the corresponding recipe information, the corresponding nutritional information, and the corresponding food property information, at least one food item that incorporates the at least one positive token, wherein the at least one positive token is associated with the positive sentiment expressed by the user; and

program instructions to continuously update a recommendation list including the at least one food item having a preparation information to resemble the at least one positive token to the user.

9. The computer system of claim 8 , further comprising:

program instructions to receive at least one image related to the user;

program instructions to define the positive user sentiment with respect to the at least one image based on machine learning techniques; and

program instructions to apply image analysis on the at least one image to identify the at least one factor that correlates with the positive user sentiment.

10. The computer system of claim 8 , further comprising:

program instructions to receive a brain state data related to the user;

program instructions to define the positive user sentiment with respect to the brain state data based on machine learning techniques; and

program instructions to apply an analysis on the brain state data to identify the at least one factor that correlates with the positive user sentiment.

11. The computer system of claim 8 , wherein the at least one factor that correlates with the positive user sentiment is selected from the group consisting of:

a theme, a subject, an object, a person, an activity, a setting, an environmental condition, and a time of day.

12. The computer system of claim 10 , wherein the program instructions to receive the brain state data comprises:

program instructions to monitor the brain state data while the user eats a particular food item; and

program instructions to store the brain state data as being associated with the particular food item.

13. The computer system of claim 11 , wherein the program instructions to analyze the plurality of user information sources related to the user is selected from the group consisting of:

program instructions to perform image analysis, program instructions to perform text analysis, program instructions to perform natural language processing, program instructions to perform semantic analysis, program instructions to perform sentiment analysis, program instructions to perform rule-based analysis, and program instructions to perform machine learning-based analysis.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 18, 2017
From: KOCHURA, NADIYA; LU, FANG
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 042042/0327 →
Continuity (1)
Related Publication 20180300460A1 · Oct 18, 2018